health-mate@1.5.4
CAUTION· static onlyPublisher claims: "Executable OpenClaw health-report skill with Chinese, English, and Japanese report flows. It reads Markdown logs only from an explicitly configured MEMORY_DI..." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-17 and scored it 49/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
…R, writes reports and logs locally, can create a commented project-local config/.env template during setup, sanitizes local-LLM stdout before AI commentary is embed…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if [ -f "${CONFIG_DIR}/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."next_step": "If you want push delivery, review the env block in config/user_config.example.json and then edit config/.env to add your webhooks.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(command, capture_output=True, text=True, env=env, timeout=180)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.req = urllib.request.Request(f'https://api.telegram.org/bot{TG_BOT_TOKEN}/sendMessage', data=data, headers={'Content-Type': 'application/json'})Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.req = urllib.request.Request(f'https://api.telegram.org/bot{TG_BOT_TOKEN}/sendMessage', data=data, headers={'Content-Type': 'application/json'})Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.source "${CONFIG_DIR}/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if [ -f "${CONFIG_DIR}/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- the setup wizard can create a commented project-local `config/.env` template if the file does not already existFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."fallback": {"zh-CN": "\u6765\u6e90\uff1a\u672c\u5730\u89c4\u5219", "en-US": "Source: local rules", "ja-JP": "出典: ローカルルール"},Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.'local': localize('\u6765\u6e90\uff1a\u672c\u5730\u89c4\u5219', 'Source: local rules'),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.echo "Warning: .env was not found. Default values will be used."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- use the top-level `env` block inside `config/user_config.example.json` as the upload-safe reference templateFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."env_set_memory_dir": "config/.env に MEMORY_DIR='/path/to/memory' を設定してください。ClawHub 手動アップロード時は config/user_config.example.json の env ブロックを参照してください。",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.- may rely on `config/user_config.example.json` as the upload-safe env reference during manual installationFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.…ment": "Upload-safe env reference. ClawHub manual upload may not include config/.env.example, so please use this block as the reference. The setup wizard will creat…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- keep only the keys you intend this skill to read inside project-local `config/.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f"Created a commented config/.env template: {env_path}",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_path = CONFIG_DIR / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if [ -f "${CONFIG_DIR}/.env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.source "${CONFIG_DIR}/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo "Warning: .env was not found. Default values will be used."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo "Warning: .env was not found. Default values will be used."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.source "${CONFIG_DIR}/.env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.'fallback': localize('\u6765\u6e90\uff1a\u672c\u5730\u89c4\u5219', 'Source: local rules'),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.- runtime scripts still read project-local `config/.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Load environment variables from .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- `config/.env.example` may be missing from the uploaded packageFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."next_step": "如需推送消息,请参考 config/user_config.example.json 中的 env 配置块,并手动编辑 config/.env 填写 Webhook。",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f"コメント付きの config/.env テンプレートを作成しました: {env_path}",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."env_set_memory_dir": "请在 config/.env 文件中设置 MEMORY_DIR='/path/to/memory',ClawHub 手动上传时可参考 config/user_config.example.json 中的 env 配置。",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Load project-local config/.env without overriding already exported variables."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.f"已生成带注释的 config/.env 模板:{env_path}",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.env_path = CONFIG_DIR / '.env'Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."env_set_memory_dir": "Set MEMORY_DIR='/path/to/memory' in config/.env. For ClawHub manual uploads, refer to the env block inside config/user_config.example.json.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.… "_comment": "Sample Health-Mate configuration. Copy this file to user_config.json and replace the demo values with your own settings. Multiple conditions, custom scoring modules, and medication tracking are supported. For ClawHub manual u…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why."# This file stays in config/.env and may contain secrets. Keep only the keys you intend the skill to read.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.req = urllib.request.Request(f'https://api.telegram.org/bot{TG_BOT_TOKEN}/sendMessage', data=data, headers={'Content-Type': 'application/json'})Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.#!/usr/bin/env python3Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…l env block below. The setup wizard can create a commented project-local config/.env file from these keys when the file does not already exist.", "_version": "1…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.…f}g で、推奨上限 {fat_max}g を上回りました。", ), 'action': localize('\u660e\u65e5\u51cf\u5c11\u6cb9\u70b8\u3001\u80a5\u8089\u3001\u5976\u6cb9\u548c\u91cd\u6cb9\u9171\u6c41\u3002', 'Cut fried food, fatty meat, cream, and oily sauces tomorrow.', '明日は揚げ物、…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.f"\u4eca\u65e5\u8102\u80aa {fat_val:.1f}g\uff0c\u9ad8\u4e8e\u5efa\u8bae\u4e0a\u9650 {fat_max}g\u3002",Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.'item': localize('\u8102\u80aa\u6444\u5165\u504f\u9ad8', 'Fat intake high', '脂質摂取が高め'),Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own."local": {"zh-CN": "\u6765\u6e90\uff1a\u672c\u5730\u89c4\u5219", "en-US": "Source: local rules", "ja-JP": "出典: ローカルルール"},Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
31 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim tankeito: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Telegram Bot API URL≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.